update-swiftui-apis
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions.
- Ingestion points: The skill uses MCP tools like
fetchAppleDocumentation,fetchExternalDocumentation, andfetchAppleVideoTranscriptto ingest content from documentation paths and external URLs specified inreferences/scan-manifest.md. - Boundary markers: There are no instructions to the agent to treat external content as untrusted or to wrap the ingested content in protective delimiters (e.g., XML tags or specific block quotes) to prevent it from influencing the agent's behavior.
- Capability inventory: The skill includes the capability to write to the filesystem (
swiftui-expert-skill/references/latest-apis.md) and perform repository operations such as creating branches and opening pull requests via thegh(GitHub) CLI. - Sanitization: The instructions do not specify any validation or sanitization steps for the content retrieved from external sources before it is formatted and committed to the repository.
Audit Metadata